{"id":"https://openalex.org/W1993755899","doi":"https://doi.org/10.1371/journal.pcbi.1000411","title":"Getting Started in Text Mining: Part Two","display_name":"Getting Started in Text Mining: Part Two","publication_year":2009,"publication_date":"2009-07-30","ids":{"openalex":"https://openalex.org/W1993755899","doi":"https://doi.org/10.1371/journal.pcbi.1000411","mag":"1993755899","pmid":"https://pubmed.ncbi.nlm.nih.gov/19649304"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1000411","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1000411","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1000411&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1000411&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004739989","display_name":"Andrey Rzhetsky","orcid":"https://orcid.org/0000-0001-6959-7405"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrey Rzhetsky","raw_affiliation_strings":["University of Chicago, Chicago, Illinois, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, Illinois, United States of America","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004654733","display_name":"Michael Seringhaus","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Seringhaus","raw_affiliation_strings":["Yale University, New Haven, Connecticut, United States of America"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, Connecticut, United States of America","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042321575","display_name":"Mark Gerstein","orcid":"https://orcid.org/0000-0002-9746-3719"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark B. Gerstein","raw_affiliation_strings":["Yale University, New Haven, Connecticut, United States of America"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, Connecticut, United States of America","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042321575"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":1.3418,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.79117551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":"7","first_page":"e1000411","last_page":"e1000411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9793000221252441,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5836105942726135},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5429674386978149},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5009911060333252},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47544336318969727},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.45920923352241516},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.426017701625824},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38362711668014526},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.2539800703525543},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1947176158428192},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11608496308326721},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10827848315238953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5836105942726135},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5429674386978149},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5009911060333252},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47544336318969727},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.45920923352241516},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.426017701625824},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38362711668014526},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.2539800703525543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1947176158428192},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11608496308326721},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10827848315238953},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1371/journal.pcbi.1000411","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1000411","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1000411&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},{"id":"pmid:19649304","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19649304","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:uchicago.tind.io:8237","is_oa":true,"landing_page_url":"http://knowledge.uchicago.edu/record/8237","pdf_url":null,"source":{"id":"https://openalex.org/S4306402460","display_name":"Knowledge@UChicago (University of Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40347166","host_organization_name":"University of Chicago","host_organization_lineage":["https://openalex.org/I40347166"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://knowledge.uchicago.edu/record/8237","raw_type":"Text"},{"id":"pmh:oai:biblioboard.com:dd263ca8-1559-4969-ac93-0f95881a9f49","is_oa":true,"landing_page_url":"https://openresearchlibrary.org/viewer/dd263ca8-1559-4969-ac93-0f95881a9f49","pdf_url":null,"source":{"id":"https://openalex.org/S4306401131","display_name":"BiblioBoard Library Catalog (Open Research Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MODID-55c385867f4:Public Library of Science (PLOS)","raw_type":"ARTICLE"},{"id":"pmh:oai:doaj.org/article:d3a0e1a8293d4304a97becc60b956d3e","is_oa":true,"landing_page_url":"https://doaj.org/article/d3a0e1a8293d4304a97becc60b956d3e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 5, Iss 7, p e1000411 (2009)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:1492580","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2709911","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1000411","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1000411","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1000411&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1993755899.pdf","grobid_xml":"https://content.openalex.org/works/W1993755899.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W41167430","https://openalex.org/W1592736283","https://openalex.org/W2005156715","https://openalex.org/W2014849717","https://openalex.org/W2031868269","https://openalex.org/W2050028106","https://openalex.org/W2073857055","https://openalex.org/W2074133193","https://openalex.org/W2096876337","https://openalex.org/W2103477204","https://openalex.org/W2115504560","https://openalex.org/W2117663476","https://openalex.org/W2129708744","https://openalex.org/W2134015035","https://openalex.org/W2149803936","https://openalex.org/W2152211274","https://openalex.org/W2161548889","https://openalex.org/W2409132800","https://openalex.org/W6635588529"],"related_works":["https://openalex.org/W2887358545","https://openalex.org/W4241083716","https://openalex.org/W2914463643","https://openalex.org/W2082438799","https://openalex.org/W2096951189","https://openalex.org/W3185751515","https://openalex.org/W1966986837","https://openalex.org/W2360138227","https://openalex.org/W2012531322","https://openalex.org/W2061327015"],"abstract_inverted_index":{"We":[0],"are,":[1],"in":[2,6],"a":[3,17,31,42],"sense,":[4],"drowning":[5],"information.":[7],"Today,":[8],"it":[9],"is":[10],"unusual":[11],"for":[12],"scientists":[13],"even":[14,30],"to":[15,20,23,29,59,73,80],"read":[16],"journal":[18],"cover":[19],"cover\u2014much":[21],"less":[22],"personally":[24],"parse":[25],"all":[26],"information":[27],"pertinent":[28],"narrow":[32],"research":[33],"area.":[34],"Increasingly":[35],"complex":[36],"content,":[37],"large":[38],"digital":[39],"supplements,":[40],"and":[41,62],"staggering":[43],"volume":[44],"of":[45,69,89],"publications":[46],"are":[47],"now":[48],"threatening":[49],"old-fashioned":[50],"scientific":[51],"reading":[52],"with":[53],"extinction.":[54],"But":[55],"by":[56],"using":[57],"computers":[58],"sift":[60],"through":[61],"scour":[63],"published":[64],"articles,":[65],"the":[66,75,83],"nascent":[67],"technology":[68],"text":[70],"mining":[71],"promises":[72],"automate":[74],"rote":[76],"information-gathering":[77],"stage\u2014hopefully":[78],"leaving":[79],"human":[81],"minds":[82],"more":[84],"challenging":[85],"(and":[86],"rewarding)":[87],"activity":[88],"higher":[90],"thinking.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
